Deep learning-enabled realistic virtual histology with ultraviolet photoacoustic remote sensing microscopy

Matthew T. Martell, Nathaniel J. M. Haven, Brendyn D. Cikaluk, Brendon S. Restall, Ewan A. McAlister, Rohan Mittal, Benjamin A. Adam, Nadia Giannakopoulos, Lashan Peiris, Sveta Silverman, Jean Deschenes, Xingyu Li and Roger J. Zemp ()
Additional contact information
Matthew T. Martell: University of Alberta
Nathaniel J. M. Haven: University of Alberta
Brendyn D. Cikaluk: University of Alberta
Brendon S. Restall: University of Alberta
Ewan A. McAlister: University of Alberta
Rohan Mittal: University of Alberta
Benjamin A. Adam: University of Alberta
Nadia Giannakopoulos: University of Alberta
Lashan Peiris: University of Alberta
Sveta Silverman: University of Alberta
Jean Deschenes: University of Alberta
Xingyu Li: University of Alberta
Roger J. Zemp: University of Alberta

Nature Communications, 2023, vol. 14, issue 1, 1-17

Abstract: Abstract The goal of oncologic surgeries is complete tumor resection, yet positive margins are frequently found postoperatively using gold standard H&E-stained histology methods. Frozen section analysis is sometimes performed for rapid intraoperative margin evaluation, albeit with known inaccuracies. Here, we introduce a label-free histological imaging method based on an ultraviolet photoacoustic remote sensing and scattering microscope, combined with unsupervised deep learning using a cycle-consistent generative adversarial network for realistic virtual staining. Unstained tissues are scanned at rates of up to 7 mins/cm2, at resolution equivalent to 400x digital histopathology. Quantitative validation suggests strong concordance with conventional histology in benign and malignant prostate and breast tissues. In diagnostic utility studies we demonstrate a mean sensitivity and specificity of 0.96 and 0.91 in breast specimens, and respectively 0.87 and 0.94 in prostate specimens. We also find virtual stain quality is preferred (P = 0.03) compared to frozen section analysis in a blinded survey of pathologists.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/s41467-023-41574-2 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-41574-2

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-023-41574-2

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().